• Journal of Chest Surgery
• /
• v.15 no.2
• /
• pp.148-154
• /
• 1982

The experience with operative treatment for peripheral situated solitary circumscribed lesions of the lung at the Department of Thorac. & Cardiovasc. Surg., Korea University Hospital during 8 years from March 1974, through April, 1982 was reviewed. Our criteria for Solitary pulmonary nodule were 1. Round or Ovoid shape 2. Surrounded by normal lung Parenchyme 3. Well circumscribed peripheral location 4. No other visible pulmonary diseases on chest X-ray except minimal atelectasis or pneumonitis 5. Largest diameter less than 8 cm Of the 55 patients reviewed, there were 69% of malignancy and 31% of benign pulmonary diseases. In malignancy 38 patients, there were 18 patients with squamous cell carcinoma, 8 patients with undifferentiated large cell carcinoma, 2 patients with undifferentiated small cell carcinoma, 10 patients with adenocarcinoma and patient with metastatic carcinoma. In benign pulmonary nodule 17 patients, here were 5 patients with tuberculoma, 5 patients with aspergilloma, 2 patients with A-V fistula, 1 patient with pulmonary blastoma, 1 patient with paragonimiasis, and 1 patient with lung abscess. Overall male to female occurrence ratio was 39:16, and most prevalent age incidence was 7th decades. Most frequent size distribution was 4-6 cm in diameter. All of benign diseases were cured by resection and 66% of malignancy performed operation and has 75% resectability.

• Korean Journal of Radiology
• /
• v.23 no.1
• /
• pp.139-149
• /
• 2022

Objective: To compare the effects of bone suppression imaging using deep learning (BSp-DL) based on a generative adversarial network (GAN) and bone subtraction imaging using a dual energy technique (BSt-DE) on radiologists' performance for pulmonary nodule detection on chest radiographs (CXRs). Materials and Methods: A total of 111 adults, including 49 patients with 83 pulmonary nodules, who underwent both CXR using the dual energy technique and chest CT, were enrolled. Using CT as a reference, two independent radiologists evaluated CXR images for the presence or absence of pulmonary nodules in three reading sessions (standard CXR, BSt-DE CXR, and BSp-DL CXR). Person-wise and nodule-wise performances were assessed using receiver-operating characteristic (ROC) and alternative free-response ROC (AFROC) curve analyses, respectively. Subgroup analyses based on nodule size, location, and the presence of overlapping bones were performed. Results: BSt-DE with an area under the AFROC curve (AUAFROC) of 0.996 and 0.976 for readers 1 and 2, respectively, and BSp-DL with AUAFROC of 0.981 and 0.958, respectively, showed better nodule-wise performance than standard CXR (AUAFROC of 0.907 and 0.808, respectively; p ≤ 0.005). In the person-wise analysis, BSp-DL with an area under the ROC curve (AUROC) of 0.984 and 0.931 for readers 1 and 2, respectively, showed better performance than standard CXR (AUROC of 0.915 and 0.798, respectively; p ≤ 0.011) and comparable performance to BSt-DE (AUROC of 0.988 and 0.974; p ≥ 0.064). BSt-DE and BSp-DL were superior to standard CXR for detecting nodules overlapping with bones (p < 0.017) or in the upper/middle lung zone (p < 0.017). BSt-DE was superior (p < 0.017) to BSp-DL in detecting peripheral and sub-centimeter nodules. Conclusion: BSp-DL (GAN-based bone suppression) showed comparable performance to BSt-DE and can improve radiologists' performance in detecting pulmonary nodules on CXRs. Nevertheless, for better delineation of small and peripheral nodules, further technical improvements are required.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.1
• /
• pp.347-370
• /
• 2019

In the computer-aided detection (CAD) system of pulmonary nodules, a high false positive rate is common because the density and the computed tomography (CT) values of the vessel and the nodule in the CT images are similar, which affects the detection accuracy of pulmonary nodules. In this paper, a method of automatic detection of pulmonary nodules based on multi-scale enhancement filters and 3D shape features is proposed. The method uses an iterative threshold and a region growing algorithm to segment lung parenchyma. Two types of multi-scale enhancement filters are constructed to enhance the images of nodules and blood vessels in 3D lung images, and most of the blood vessel images in the nodular images are removed to obtain a suspected nodule image. An 18 neighborhood region growing algorithm is then used to extract the lung nodules. A new pulmonary nodules feature descriptor is proposed, and the features of the suspected nodules are extracted. A support vector machine (SVM) classifier is used to classify the pulmonary nodules. The experimental results show that our method can effectively detect pulmonary nodules and reduce false positive rates, and the feature descriptor proposed in this paper is valid which can be used to distinguish between nodules and blood vessels.

• Tuberculosis and Respiratory Diseases
• /
• v.41 no.4
• /
• pp.435-439
• /
• 1994

Lung cancer is the most common fatal malignant lesion in both sexes. Detection of the solitary pulmonary nodule is important because surgical series up to a third of solitary pulmonary nodules are bronchogenic carcinoma. Bronchioloalveolar cell carcinoma is a rare primary lung cancer and surgery is treatment of choice in brochioloalveolar cell carcinoma. We experinced a case of bronchioloalveolar cell carcinoma in solitary pulmonary nodule with cavitary lesion in chest CT scan, which is an uncommon finding in brochioloalveolar cell carcinoma.

• Journal of Chest Surgery
• /
• v.46 no.4
• /
• pp.316-318
• /
• 2013

Thoracoscopic needle aspiration is a good alternative for a centrally-located solitary pulmonary nodule (SPN) suspected of being lung cancer without severe pleural adhesion. The authors report the technique of thoracoscopic needle aspiration biopsy in a SPN just in the medial aspect of the truncus anterior pulmonary artery and the right upper lobe bronchus.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.46 no.6
• /
• pp.35-43
• /
• 2009

In the Computer Aided Diagnosis(CAD) System, the efficient way of classifying nodules from chest CT images of a patient is to perform the classification of the remaining part after the pulmonary vessel extraction. During the pulmonary vessel extraction, due to the small difference between the vessel and nodule features in imaging studies such as CT scans after having an injection of contrast, nodule maybe extracted along with the pulmonary vessel. Therefore, the pulmonary vessel extraction method plays an important role in the nodule classification process. In this paper, we propose a nodule reclassification method based on vessel thickness analysis. The proposed method consist of four steps, lung region searching step, vessel extraction and thinning step, vessel topology formation and correction step and the reclassification of nodule in the vessel candidate step. The radiologists helped us to compare the accuracy of the CAD system using the proposed method and the accuracy of general one. Experimental results show that the proposed method can extract pulmonary vessels and reclassify false-positive nodules accurately.

• Tuberculosis and Respiratory Diseases
• /
• v.64 no.4
• /
• pp.318-323
• /
• 2008

It is difficult to distinguish a lung cancer from a pulmonary tuberculoma or other benign nodule. It is even more difficult to identify the type of lesion if the mass shows no change in size or demonstrates slow growth. Only a pathological confirmation can possibly reveal the nature of the lesion. A 61-year-old-woman was referred for a solitary pulmonary nodule. The nodule showed no change in size for the first two years and continued to grow slowly. Pathological and immunological analyses were conducted for confirmation of the nodule. The nodule was identified as a well-differentiated primary pulmonary adenocarcinoma. An LULobectomy was performed, and the post surgical stage of the nodule was IIIA (T2N2M0). Even though there are few risk factors, there is still the possibility of a malignancy in cases of non-growing or slow growing solitary pulmonary nodules. Therefore, pathological confirmation is encouraged to obtain a firm diagnosis.

• Journal of Chest Surgery
• /
• v.28 no.5
• /
• pp.495-498
• /
• 1995

Pulmonary arteriovenous fistula can be either congenital or acquired. The vast majority are congenital, and about 60% have been associated with hereditary hemorrhagic telangiectasia [Rendu-Osler-Weber disease . Secondary or acquired pulmonary arteriovenous fistula occurs with trauma, schistosomiasis, long-standing hepatic cirrhosis, metastatic carcinoma, and actinomycosis. Pulmonary hemorrhage secondary to acquired pulmonary arteriovenous fistula is a rare event associated with mortality. We have experienced 64 year-old female patient with the hemoptysis secondary to acquired pulmonary arteriovenous fistula due to the infection of pulmonary parasite. The chest PA and CT scan was showed calcified nodule to the distal portion of lateral segmental bronchus of RML. The bronchial angiogram was demonstrated slightly hypertrophied bronchial artery supplying RML bronchus and the presence of hypervascularization around the calcified nodule, rapid A-V shunting is noted by fluoroscopy. The patient was successfully treated by the right middle lobectomy.

• Tuberculosis and Respiratory Diseases
• /
• v.47 no.4
• /
• pp.498-506
• /
• 1999

Background : The causes of solitary pulmonary nodule are many, but the main concern is whether the nodule is benign or malignant. Because a solitary pulmonary nodule is the initial manifestation of the majority of lung cancer, accurate clinical and radiologic interpretation is important. Bayes' theorem is a simple method of combining clinical and radiologic findings to estimate the probability that a nodule in an individual patients is malignant. We estimated the probability of malignancy of solitary pulmonary nodules with a specific combination of features by Bayesian approach. Method : One hundred and eighty patients with solitary pulmonary nodules were identified from multi-center analysis. The hospital records of these patients were reviewed and patient age, smoking history, original radiologic findings, and diagnosis of the solitary pulmonary nodules were recorded. The diagnosis of solitary pulmonary nodule was established pathologically in all patients. We used to Bayes' theorem to devise a simple scheme for estimating the likelihood that a solitary pulmonary nodule is malignant based on radiological and clinical characteristics. Results : In patients characteristics, the probability of malignancy increases with advancing age, peaking in patients older than 66 year of age(LR : 3.64), and higher in patients with smoking history more than 46 pack years(LR : 8.38). In radiological features, the likelihood ratios were increased with increasing size of the nodule and nodule with lobulated or spiculated margin. Conclusion : In conclusion, the likelihood ratios of malignancy may improve the accuracy of the probability of malignancy, and can be a guide of management of solitary pulmonary nodule.

• Journal of the Korean Society of Radiology
• /
• v.85 no.4
• /
• pp.705-713
• /
• 2024

This article discusses studies and real-world experiences related to the clinical application of artificial intelligence-based computer-aided detection (AI-CAD) software (LuCAS-plus, Monitor Corporation) in detecting pulmonary nodules. During clinical trials for lung cancer screening, AI-CAD exhibited performance comparable to that of medical professionals in terms of sensitivity and specificity. Studies revealed that applying AI-CAD for diagnosing pulmonary metastases led to high detection rates. The use of a nodule matching algorithm in diagnosing pulmonary metastases significantly reduced false non-metastasis results. In clinical settings, implementing AI-CAD enhanced the efficiency of pulmonary nodule detection, saving time and effort during CT reading. Overall, AI-CAD is expected to offer substantial support for lung cancer screening and the interpretation of chest CT scans for malignant tumor surveillance.